🔄 In a Training Loop
Nishith Jain
KingNish
AI & ML interests
AI is fun actually.
Recent Activity
liked a model 10 days ago
rycerzes/Qwen3.5-4B-Decision upvoted an article 10 days ago
Building long-horizon SWE environments on Hugging Face: Frontier SWE × OpenEnv liked a Space 15 days ago
KingNish/paradee-webOrganizations
-
Large Language Models Think Too Fast To Explore Effectively
Paper • 2501.18009 • Published • 23 -
s1: Simple test-time scaling
Paper • 2501.19393 • Published • 126 -
Scalable-Softmax Is Superior for Attention
Paper • 2501.19399 • Published • 24 -
SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers
Paper • 2502.20545 • Published • 22
Collection of TOP Open Source LLM, Sort by Best on top
-
meta-llama/Llama-3.1-405B-Instruct
Text Generation • 406B • Updated • 9.69k • 607 -
mistralai/Mistral-Large-Instruct-2407
123B • Updated • 12.7k • 870 -
meta-llama/Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 93.9k • • 1.03k -
Qwen/Qwen2-72B-Instruct
Text Generation • 73B • Updated • 24.3k • • 724
Contains spaces which gives lightning fast results compare to others.
-
Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding
Paper • 2402.05109 • Published • 2 -
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Paper • 2401.10774 • Published • 60 -
Better & Faster Large Language Models via Multi-token Prediction
Paper • 2404.19737 • Published • 80 -
Exploring the Latent Capacity of LLMs for One-Step Text Generation
Paper • 2505.21189 • Published • 61
Collection of top mini llms
-
KingNish/Qwen2.5-0.5b-Test-ft
Text Generation • 0.5B • Updated • 111 • • 12 -
meta-llama/Llama-3.2-1B-Instruct
Text Generation • 1B • Updated • 1.77M • • 1.95k -
Qwen/Qwen2.5-1.5B-Instruct
Text Generation • 2B • Updated • 4.68M • • 929 -
Qwen/Qwen2.5-0.5B-Instruct
Text Generation • 0.5B • Updated • 4.76M • • 732
-
Agent Workflow Memory
Paper • 2409.07429 • Published • 32 -
MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis
Paper • 2409.07129 • Published • 8 -
Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance
Paper • 2409.04593 • Published • 26 -
Imagine yourself: Tuning-Free Personalized Image Generation
Paper • 2409.13346 • Published • 69
-
Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding
Paper • 2402.05109 • Published • 2 -
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Paper • 2401.10774 • Published • 60 -
Better & Faster Large Language Models via Multi-token Prediction
Paper • 2404.19737 • Published • 80 -
Exploring the Latent Capacity of LLMs for One-Step Text Generation
Paper • 2505.21189 • Published • 61
-
Large Language Models Think Too Fast To Explore Effectively
Paper • 2501.18009 • Published • 23 -
s1: Simple test-time scaling
Paper • 2501.19393 • Published • 126 -
Scalable-Softmax Is Superior for Attention
Paper • 2501.19399 • Published • 24 -
SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers
Paper • 2502.20545 • Published • 22
Collection of TOP Open Source LLM, Sort by Best on top
-
meta-llama/Llama-3.1-405B-Instruct
Text Generation • 406B • Updated • 9.69k • 607 -
mistralai/Mistral-Large-Instruct-2407
123B • Updated • 12.7k • 870 -
meta-llama/Llama-3.1-70B-Instruct
Text Generation • 71B • Updated • 93.9k • • 1.03k -
Qwen/Qwen2-72B-Instruct
Text Generation • 73B • Updated • 24.3k • • 724
Collection of top mini llms
-
KingNish/Qwen2.5-0.5b-Test-ft
Text Generation • 0.5B • Updated • 111 • • 12 -
meta-llama/Llama-3.2-1B-Instruct
Text Generation • 1B • Updated • 1.77M • • 1.95k -
Qwen/Qwen2.5-1.5B-Instruct
Text Generation • 2B • Updated • 4.68M • • 929 -
Qwen/Qwen2.5-0.5B-Instruct
Text Generation • 0.5B • Updated • 4.76M • • 732
Contains spaces which gives lightning fast results compare to others.
-
Agent Workflow Memory
Paper • 2409.07429 • Published • 32 -
MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis
Paper • 2409.07129 • Published • 8 -
Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance
Paper • 2409.04593 • Published • 26 -
Imagine yourself: Tuning-Free Personalized Image Generation
Paper • 2409.13346 • Published • 69